Pinned Tweet
Run @opencode in the cloud
Your laptop goes to sleep, OpenCode keeps going
Now available on Atomic Bot -> atomicbot.ai/opencode
Your laptop goes to sleep, OpenCode keeps going
Now available on Atomic Bot -> atomicbot.ai/opencode
5
12
94
9,877
@pidotdev Big love to @badlogicgames @mitsuhiko @davidbrai @vegardstikbakke and the whole @pidotdev team, we’re big fans of Pi and the way you build it
0
0
0
73
Run Pi @pidotdev in the cloud
Your minimal agent working while your laptop sleeps
Try Pi → atomicbot.ai/pi-agent-in-cl…
Your minimal agent working while your laptop sleeps
Try Pi → atomicbot.ai/pi-agent-in-cl…
4
3
15
858
@opencode Big love to @thdxr @jayair @adamdotdev @kitlangton and the whole @opencode team, we’re huge fans of what you’re building
0
0
2
334
Don't want to send everything to the cloud?
We just launched our local AI agent. So proud of the Atomic Agent team!
Download → atomicagent.io
We just launched our local AI agent. So proud of the Atomic Agent team!
Download → atomicagent.io
Meet Atomic Agent Desktop!
✦ Local AI-first agent for Mac, Windows & Linux
✦ 4x bigger context window on local models with TurboQuant
✦ Atomic Fusion orchestrates cloud and local models to reduce costs
Download Free & Private Agent → atomicagent.io
2
4
16
947
Save money on your agents
Now you can control what they spend on models in Usage & Billing
One click and any agent is live 24/7 in the cloud!
Now you can control what they spend on models in Usage & Billing
One click and any agent is live 24/7 in the cloud!
9
10
34
29,185
NanoClaw is now available on Atomic Bot!
A security agent that asks before it does anything.
One click and @NanoClaw_AI is live 24/7 in the cloud!
A security agent that asks before it does anything.
One click and @NanoClaw_AI is live 24/7 in the cloud!
2
5
28
2,283
Mercury Agent is now available on Atomic Bot!
Say it once and every session after already has your context. The longer you work together, the less you have to explain.
One click and @mercury__agent is live 24/7 in the cloud!
Say it once and every session after already has your context. The longer you work together, the less you have to explain.
One click and @mercury__agent is live 24/7 in the cloud!
8
8
30
27,985
Fable 5.1 crushed GPT-5.6 Sol at rebuilding Claude's release video!
Outputs:
• Claude Fable 5.1: 3 versions, 9.36M tokens, $22.70
• GPT-5.6 Sol: 1 version, 1.47M tokens, $0.83
Fable checked its own render against its own shot list, found five places where it had got itself ce before calling it done, while GPT shipped version one for 27 times less.
Try Claude Fable 5.1 on Atomic Bot in one click!
Outputs:
• Claude Fable 5.1: 3 versions, 9.36M tokens, $22.70
• GPT-5.6 Sol: 1 version, 1.47M tokens, $0.83
Fable checked its own render against its own shot list, found five places where it had got itself ce before calling it done, while GPT shipped version one for 27 times less.
Try Claude Fable 5.1 on Atomic Bot in one click!
We’re introducing Claude Fable 5.1 and Claude Mythos 5.1.
They're the world’s most advanced models for coding and knowledge work.
4
6
99
20,014
OpenClaw 2.0 is available on Atomic Bot!
We ran a battle: OpenClaw 2.0 vs Hermes Agent on GLM 5.3. Four prompts: movie scenes with the OpenClaw mascot in the lead role.
Outputs:
OpenClaw 2.0: ~2.1M tokens, ~$4.5, 10 self-fixes
Hermes Agent: ~2.9M tokens, ~$4, 20 self-fixes
its own frames at exact timestamps, counted pixels to check its work, and filed fixes like "coat tail whip direction was inverted". Hermes went further and built itself a render harness: it measured frame times, checked the loop seam was invisible, and audited every scene against the spec before we ever opened it. That double-checking is where its extra tokens went.
Run OpenClaw 2.0 in the cloud via Atomic Bot in one click!
We ran a battle: OpenClaw 2.0 vs Hermes Agent on GLM 5.3. Four prompts: movie scenes with the OpenClaw mascot in the lead role.
Outputs:
OpenClaw 2.0: ~2.1M tokens, ~$4.5, 10 self-fixes
Hermes Agent: ~2.9M tokens, ~$4, 20 self-fixes
its own frames at exact timestamps, counted pixels to check its work, and filed fixes like "coat tail whip direction was inverted". Hermes went further and built itself a render harness: it measured frame times, checked the loop seam was invisible, and audited every scene against the spec before we ever opened it. That double-checking is where its extra tokens went.
Run OpenClaw 2.0 in the cloud via Atomic Bot in one click!
OpenClaw 2.0 has arrived
openclaw.ai/blog/openclaw-…
20
9
99
68,547
Run Codex 24/7 in the cloud with Atomic Bot!
Just hand it a repo and close the laptop. One click to start.
We ran it on ours first and it found a bug nobody had answered. Codex fixed it before we got back.
Just hand it a repo and close the laptop. One click to start.
We ran it on ours first and it found a bug nobody had answered. Codex fixed it before we got back.
21
8
66
28,694
atomicbot.ai retweeted
Run Qwen3.8 27B locally via Atomic Chat💥
We released Atomic Dynamic GGUF quants, from 8-bit (28.9 GB) down to 1-bit (8.5 GB), and measured all other Qwen3.8 GGUFs in the community
AD-IQ3_S runs on a 16GB MacBook Air and picks the same next token as the BF16 original 92.4% of the time
We released Atomic Dynamic GGUF quants, from 8-bit (28.9 GB) down to 1-bit (8.5 GB), and measured all other Qwen3.8 GGUFs in the community
AD-IQ3_S runs on a 16GB MacBook Air and picks the same next token as the BF16 original 92.4% of the time
We promised open weights for Qwen3.8. Now, time to meet them! 🎉
⚡ Qwen3.8-27B:
- A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world coding & office workflows.
- 262K native context, easily extendable to 1M toker builders. Highly efficient, high-quality, and licensed under Apache 2.0.
🚀 The open weights for Qwen3.8-2.4T-A95B (Max-level) have also been released recently.
Whether you're shipping lightweight applications with Qwen3.8-27B locally or building agents with Qwen3.8-2.4T-A95B, they're yours now!
Download, deploy, and build something we haven't imagined yet. 👀👇
- Hugging Face：
huggingface.co/collections/Qw…
- ModelScope：
modelscope.cn/collections/Qw…
61
145
1,219
520,319